sourcegraph-search

Fail

Audited by Snyk on Feb 16, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.80). The skill explicitly includes searches for hardcoded credentials and exposes code search results (which may contain literal secret strings), so an agent using it may need to return secret values verbatim from repo matches.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). This skill uses the Sourcegraph CLI (e.g., src search examples like repo:github.com/... and visibility:public) and JSON/WebFetch output to fetch and parse code and file contents from public repositories and arbitrary repo URLs, meaning the agent will ingest untrusted, user-generated third‑party content as part of its workflow.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 03:11 AM